Sciweavers

2190 search results - page 72 / 438
» Learning Relations Using Collocations
Sort
View
ECML
1998
Springer
13 years 12 months ago
First-Order Learning for Web Mining
We present compelling evidence that the World Wide Web is a domain in which applications can benefit from using first-order learning methods, since the graph structure inherent in ...
Mark Craven, Seán Slattery, Kamal Nigam
ILP
2004
Springer
14 years 1 months ago
Improving Rule Evaluation Using Multitask Learning
Abstract. This paper introduces Deft, a new multitask learning approach for rule learning algorithms. Like other multitask learning systems, the one proposed here is able to improv...
Mark D. Reid
IROS
2007
IEEE
157views Robotics» more  IROS 2007»
14 years 2 months ago
Autonomous blimp control using model-free reinforcement learning in a continuous state and action space
— In this paper, we present an approach that applies the reinforcement learning principle to the problem of learning height control policies for aerial blimps. In contrast to pre...
Axel Rottmann, Christian Plagemann, Peter Hilgers,...
COLCOM
2007
IEEE
14 years 2 months ago
Peer2Schedule - an experimental peer-to-peer application to support present collaboration
Abstract—This paper describes experiences from implementing an experimental mobile peer-to-peer application called Peer2Schedule aimed at improving and supporting collaboration w...
Alf Inge Wang, Peter Nicolai Motzfeldt
ACL
2008
13 years 9 months ago
The Tradeoffs Between Open and Traditional Relation Extraction
Traditional Information Extraction (IE) takes a relation name and hand-tagged examples of that relation as input. Open IE is a relationindependent extraction paradigm that is tail...
Michele Banko, Oren Etzioni